WSi News2016-04-06 12:59:06
New Patent Affords More Accurate Video Detection and Fewer False Alarms
Moving backgrounds can be a difficult problem for video detection algorithms. The newly awarded patent for PureTech Systems addresses many of these issues.
Within the field of video analytics, "background modeling" refers to the ability to understand normal movement that may occur in a scene, such as vegetation movement, lighting changes, flowing water or even the passing of a subway train. Having a keen understanding of the changing background, allows for more accurate target detection, and more importantly, a reduction in false alarms. One significant claim of the new patent is that no assumption about the nature of the background is required. The software and/or installer does not need to concern themseleves with the type of scene for which the algorithm will be utilized.
More specifically, the pixel-based multimodal background model makes no assumption about the number of modes or functional forms of the underlying distributions while exploiting radiometric information along with gradient magnitude and orientation through one, or a host, of such models to adapt to backgrounds that change with multitude of periodicities over the same or different regions of the scene while remaining geospatial-aware.
An additional, and perhaps more important, aspect of the patent is that it lends itself to deployment on PTZs, and video cameras mounted on mobile platforms including, ground vehicles (trucks, trains, AGVs-Automated Guided Vehicles), waterborne vessels and aerial platforms (including AGVs, aerostats). The act of steering a PTZ camera, or the movement of a vehicle or platform on which a camera is mounted, results in a constantly moving background, for which this patent applies. In the same manner as the patent provides claims for a fixed scene with a changing background, it also applies to background movement induced by changing the position of the camera.
"PureTech Systems continues to be a pioneer in the development of new capability in the field of video analytics," notes Larry Bowe, president of PureTech Systems. "As the demand for intelligent video increases, so does the complexity of the scenes and the variety of methods and platforms used to collect video data," furthers Bowe. "These new market demands require continued research and development; which PureTech Systems continues to pursue."
The patent, granted on March 22, 2016, has application across multiple markets, including perimeter security, defense, geo-intelligence/GEOINT applications, border, military, retail, transportation, manufacturing and consumer.
Moving backgrounds can be a difficult problem for video detection algorithms. The newly awarded patent for PureTech Systems addresses many of these issues.
Within the field of video analytics, "background modeling" refers to the ability to understand normal movement that may occur in a scene, such as vegetation movement, lighting changes, flowing water or even the passing of a subway train. Having a keen understanding of the changing background, allows for more accurate target detection, and more importantly, a reduction in false alarms. One significant claim of the new patent is that no assumption about the nature of the background is required. The software and/or installer does not need to concern themseleves with the type of scene for which the algorithm will be utilized.
More specifically, the pixel-based multimodal background model makes no assumption about the number of modes or functional forms of the underlying distributions while exploiting radiometric information along with gradient magnitude and orientation through one, or a host, of such models to adapt to backgrounds that change with multitude of periodicities over the same or different regions of the scene while remaining geospatial-aware.
An additional, and perhaps more important, aspect of the patent is that it lends itself to deployment on PTZs, and video cameras mounted on mobile platforms including, ground vehicles (trucks, trains, AGVs-Automated Guided Vehicles), waterborne vessels and aerial platforms (including AGVs, aerostats). The act of steering a PTZ camera, or the movement of a vehicle or platform on which a camera is mounted, results in a constantly moving background, for which this patent applies. In the same manner as the patent provides claims for a fixed scene with a changing background, it also applies to background movement induced by changing the position of the camera.
"PureTech Systems continues to be a pioneer in the development of new capability in the field of video analytics," notes Larry Bowe, president of PureTech Systems. "As the demand for intelligent video increases, so does the complexity of the scenes and the variety of methods and platforms used to collect video data," furthers Bowe. "These new market demands require continued research and development; which PureTech Systems continues to pursue."
The patent, granted on March 22, 2016, has application across multiple markets, including perimeter security, defense, geo-intelligence/GEOINT applications, border, military, retail, transportation, manufacturing and consumer.
For more information contact:
